© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37700
    Prev
    Next
    INDEX
    Explanations

    austerity and strictness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĦ¿
    -0.12
    ruz
    -0.10
    主å¸Ń
    -0.10
    æĤłæĤł
    -0.10
    ufs
    -0.09
    rud
    -0.09
    åħĴ
    -0.09
    ä¿ij
    -0.09
    ä¸ĭæīĭ
    -0.09
    -operator
    -0.09
    POSITIVE LOGITS
    æݪæĸ½
    0.09
    zza
    0.09
    anded
    0.09
    idge
    0.08
    usterity
    0.08
    çĪ¬ä¸Ĭ
    0.08
    ech
    0.08
    onomic
    0.08
    iface
    0.08
     austerity
    0.08
    Activations Density 0.005%

    No Known Activations